Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
- huggingface
- inference
- llm
- mechanistic-interpretability
132,241 visible repositories in the index
145–168 of 255 · Most stars
Run, serve, query and edit AI models — a Rust model runtime built on VINDEX3, an executable, inspectable model format.
[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delivery.
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
Open-Source Perplexity
Editor Code Assistant (ECA) - AI pair programming capabilities agnostic of editor
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
企业级 AI 资源纳管平台,提供统一 AI网关、Token调度能力,纳管 OpenAI、Azure、Claude、DeepSeek 等主流模型,并支持 MCP 工具与 Skill 的集中注册分发。具备内外双轨定价、成本归因、统一身份认证、安全审计与效能报表,帮助企业精准控制成本、量化 ROI,高效治理 AI 资产。
OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.
The complete post-training stack for LLMs, plus RL for any problem. SFT, DPO and multi-turn agentic RL, with evolutionary hyperparameter optimization built in.
RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.
Perplexity open source garden for inference technology
Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Gemini 4 Argon from a paid account cookie, strict_model (429 instead of a silent downgrade), cookie pool with auto-renewal, proxy pool, admin panel, image & video generation, single Go binary · 把 Gemini 网页反代成 OpenAI 兼容 / Gemini 原生 API,付费号 cookie 直接用 4 Argon
Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform - Providing a complete solution for agent creation and distribution, knowledge base management, model proxy, memory system, and plugin ecosystem.
MCP Gateway is a reverse proxy and management layer for MCP servers, enabling scalable, session-aware stateful routing and lifecycle management of MCP servers in Kubernetes environments.
A lightweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.
A Burp Suite extension to add OpenAI (GPT) on Burp and help you with your Bug Bounty recon to discover endpoints, params, URLs, subdomains and more!
LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.
Chat and Ask on your own data. Accelerator to quickly upload your own enterprise data and use OpenAI services to chat to that uploaded data and ask questions
Halo is an open-source framework built by White Circle for training large language and multimodal models
🚀 Catalyst is a C# Natural Language Processing library built for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.